Sample classification method, system and medium based on multiple sample reasoning neural network

Abstract

The invention discloses a sample classification method, system and medium based on a multi-sample reasoning neural network. The method comprises the following steps: (1) establishing a multi-sample reasoning neural network MSIN; (2) taking several training samples of different sample fields as input values, inputting them into the multi-sample reasoning neural network MSIN, and training the multi-sample reasoning neural network MSIN for a specified number of rounds; after each round of training, inputting the verification samples to the MSIN for testing, and saving the MSIN which minimizes thetotal loss function of the MSIN as the final network. Step (3): taking a plurality of test samples from different sample domains as input values of the multi-sample reasoning neural network MSIN, inputting the input values into the trained multi-sample reasoning neural network, and outputting the sample categories corresponding to the test samples or the sample domains in which the test samples are located.

Description

technical field [0001] The invention relates to a sample classification method, system and medium based on a multi-sample reasoning neural network. Background technique [0002] The application of artificial intelligence in all walks of life in today's society is in the ascendant. As the most important technology of artificial intelligence, machine learning determines the application prospect and product landing of artificial intelligence. In recent years, deep learning technology based on multi-layer neural network has played a leading role in the fields of computer vision and natural language processing, making these fields develop by leaps and bounds. However, the performance of a neural network is positively correlated with the number of parameters, that is, a network with high performance often has a huge number of parameters. These networks often require dozens or even hundreds of high-performance GPU clusters for training, and high-performance GPUs are often required...

AI Technical Summary

Problems solved by technology

These networks are usually designed to expand the sample domain or measure the similarity between samples, and cannot predict the category of the sample, let alone the sample domain corresponding to the sample.

Images